- Potential Improvement in energy efficiency between 7% and 10% depending on equipment.
- Potential improvement in energy consumption by 15% approx. in support systems such as cooling.
Develop AI Technologies
Pattern analysis, prediction and intelligent classification.
- To find the power consumption pattern of the aluminum melting towers to detect possible improvements in the use of mixed raw material.
- Dataset size: 200 MB
- Number of variables: 10
- Sampling time: 1s
- By means of clustering techniques by Gaussian mixtures, it has been possible to detect the energy consumption of gas according to the raw material mixture.
- The average values, in this case, the centroids of each cluster, have been able to differentiate the 3 different groups of the most relevant average foundry mix when it comes to gas consumption.
- Additionally, a temporal analysis allows analyzing the clusters with the highest energy consumption, in the case of Figure 16, Cluster 1 is the one with the most important deviations, detailing the time slot in which it occurs.